© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 14649
    Prev
    Next
    INDEX
    Explanations

    abbreviations and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     因此
    1.03
    Tob
    1.02
     Ours
    1.02
    态
    1.01
     чином
    0.97
    ilit
    0.97
     Dosage
    0.95
    ff
    0.95
     $\%
    0.95
     Brewery
    0.94
    POSITIVE LOGITS
     temptation
    1.11
    es
    1.06
     mutually
    1.01
     unregistered
    1.00
     flickering
    0.98
     મુ
    0.97
    σκ
    0.97
     সাবেক
    0.96
    كتر
    0.96
     fluctuations
    0.95
    Activations Density 0.000%

    No Known Activations